Abstract
Predicting depth from a single image is an important problem for understanding the 3-D geometry of a scene. Recently, the nonparametric depth sampling (DepthTransfer) has shown great potential in solving this problem, and its two key components are a Scale Invariant Feature Transform (SIFT) flow–based depth warping between the input image and its retrieved similar images and a pixel-wise depth fusion from all warped depth maps. In addition to the inherent heavy computational load in the SIFT flow computation even under a coarse-to-fine scheme, the fusion reliability is also low due to the low discriminativeness of pixel-wise description nature. This article aims at solving these two problems. First, a novel sparse SIFT flow algorithm is proposed to reduce the complexity from subquadratic to sublinear. Then, a reweighting technique is introduced where the variance of the SIFT flow descriptor is computed at every pixel and used for reweighting the data term in the conditional Markov random fields. Our proposed depth transfer method is tested on the Make3D Range Image Data and NYU Depth Dataset V2. It is shown that, with comparable depth estimation accuracy, our method is 2–3 times faster than the DepthTransfer.
Highlights
Depth estimation from a single image is an important issue in 3-D scene understanding
We propose a novel sparse Scale Invariant Feature Transform (SIFT) flow algorithm, which is of sublinear time complexity and much faster than the SIFT flow
Can we estimate the discrimination by using per pixel feature descriptor? To answer this question, we propose a novel method to reweight the confidence of the conditional Markov random fields (CRFs) by combining distinctive metric of features
Summary
Depth estimation from a single image is an important issue in 3-D scene understanding. Scene depth is essential for a variety of tasks, ranging from 3-D modeling and visualization to robot navigation. In addition to parametric methods[6,7,8,9] for extracting depths, many nonparametric depth sampling approaches[10,11] have been proposed to automatically convert monocular images into stereoscopic images with good performances. Karsch et al.,[11] by exploiting the availability of a set of images with known depth, proposed a nonparametric algorithm (DepthTransfer) for depth estimation.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call